A TBM classification method and device for tunnel surrounding rock

Abstract

This invention provides a TBM (Tube-to-Mechanical) grading method and apparatus for tunnel surrounding rock. A specific implementation of the method includes: First, obtaining the abrasion index and uniaxial compressive strength of the surrounding rock to be tested, as well as the field penetration index and torque penetration index when the TBM collects data from the surrounding rock; Second, based on the abrasion index and uniaxial compressive strength of the surrounding rock, and the field penetration index and torque penetration index of the TBM, using a model for predictive processing to generate the excavability index of the surrounding rock; Then, performing preliminary grading of the surrounding rock based on the BQ (Browser-Quality) grading method to generate the actual quality index of the surrounding rock; Finally, determining the TBM grade of the surrounding rock according to the surrounding rock TBM grading table, based on the excavability index and the actual quality index of the surrounding rock. This improves the accuracy of determining the TBM grade of the surrounding rock.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, and in particular relates to a TBM classification method and device for tunnel surrounding rock. Background Technology

[0002] Current standards for classifying tunnel surrounding rock are primarily based on the mining method (commonly known as the drill-and-blast method) for determining the stability levels of tunnel surrounding rock. However, because full-face tunnel boring machines (TBMs) employ completely different construction methods and rock failure modes compared to the drill-and-blast method, simply applying the existing drill-and-blast-based tunnel surrounding rock classification methods is insufficient to meet the needs of current TBM construction conditions. Therefore, establishing a suitable surrounding rock classification method for TBM construction is of paramount importance.

[0003] This invention proposes a tunnel surrounding rock classification method suitable for TBM construction based on this problem. Summary of the Invention

[0004] To address the aforementioned problems in the existing technology, this invention provides a TBM classification method and apparatus for tunnel surrounding rock, which can accurately determine the TBM level corresponding to the surrounding rock to be tested, thereby facilitating the scheduling of surrounding rock construction and the selection of TBM equipment, and providing a decision-making basis for ensuring efficient TBM construction and cost control.

[0005] According to a first aspect of the present invention, a TBM grading method for tunnel surrounding rock is provided. The method includes: obtaining the abrasiveness index and uniaxial compressive strength of the surrounding rock to be tested, as well as the field penetration index and torque penetration index when a full-face tunnel boring machine (TBM) collects data on the surrounding rock; based on the abrasiveness index and uniaxial compressive strength of the surrounding rock to be tested, and the field penetration index and torque penetration index of the TBM, performing predictive processing using a model to generate a tunnelability index corresponding to the surrounding rock to be tested; performing preliminary grading of the surrounding rock to be tested based on the BQ grading method to generate an actual quality index corresponding to the surrounding rock to be tested; and determining the TBM grade corresponding to the surrounding rock to be tested based on the tunnelability index and the actual quality index of the surrounding rock to be tested, according to a surrounding rock TBM grading table.

[0006] According to a second aspect of the present invention, a TBM grading device for tunnel surrounding rock is provided. The device includes: an acquisition module, configured to acquire the abrasion index and uniaxial compressive strength of the surrounding rock to be tested, and the field penetration index and torque penetration index of the surrounding rock when a full-face tunnel boring machine (TBM) collects data from the surrounding rock; a prediction module, configured to generate a tunnelability index of the surrounding rock to be tested by performing prediction processing using a model based on the abrasion index and uniaxial compressive strength of the surrounding rock to be tested, and the field penetration index and torque penetration index of the TBM; a first generation module, configured to perform preliminary grading of the surrounding rock to be tested based on the BQ grading method, and generate the actual quality index of the surrounding rock to be tested; and a first determination module, configured to determine the TBM grade of the surrounding rock to be tested based on the tunnelability index and the actual quality index of the surrounding rock to be tested, according to a surrounding rock TBM grading table.

[0007] According to a third aspect of the present invention, a computer-readable medium is also provided, on which a computer program is stored, wherein the program, when executed by a processor, implements the method described in the first aspect.

[0008] This invention provides a TBM (Tunnel Boring Machine) grading method and apparatus for tunnel surrounding rock. The method includes: first, obtaining the abrasion index and uniaxial compressive strength of the surrounding rock to be tested, as well as the field penetration index and torque penetration index collected by a full-face tunnel boring machine (TBM) when collecting data from the surrounding rock; second, based on the abrasion index and uniaxial compressive strength of the surrounding rock to be tested, and the field penetration index and torque penetration index of the TBM, performing predictive processing using a model to generate the excavability index of the surrounding rock to be tested; then, performing preliminary grading of the surrounding rock to be tested based on the BQ (Brick Qasr) grading method to generate the actual quality index of the surrounding rock to be tested; finally, determining the TBM grade of the surrounding rock to be tested based on the TBM grading table, the excavability index of the surrounding rock to be tested, and the actual quality index of the surrounding rock to be tested. Therefore, this embodiment combines the excavability index of the surrounding rock to be tested with the actual quality index of the surrounding rock to be tested to determine the TBM grade of the surrounding rock to be tested; thus forming a TBM grade classification method based on the excavability and stability of the surrounding rock, thereby improving the accuracy of determining the TBM grade of the surrounding rock to be tested. Attached Figure Description

[0009] The following sections will describe some specific embodiments of the invention in detail by way of example and not limitation, with reference to the accompanying drawings. The same reference numerals in the drawings denote the same or similar parts or portions. Those skilled in the art should understand that these drawings are not necessarily drawn to scale. In the drawings:

[0010] Figure 1This is a flowchart illustrating a TBM grading method for tunnel surrounding rock according to an embodiment of the present invention.

[0011] Figure 2 This is a schematic diagram of the structure of a steel needle after wear in one embodiment of the present invention;

[0012] Figure 3 This is a schematic diagram of the structure of a TBM grading device for tunnel surrounding rock provided in an embodiment of the present invention. Detailed Implementation

[0013] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0014] like Figure 1 The diagram shown is a flowchart illustrating a TBM classification method for tunnel surrounding rock according to an embodiment of the present invention.

[0015] A TBM classification method for tunnel surrounding rock, the method comprising at least the following steps:

[0016] S101, obtain the abrasive index and uniaxial compressive strength of the surrounding rock to be tested, as well as the field penetration index and torque penetration index when the full-face tunnel boring machine (TBM) collects data on the surrounding rock to be tested.

[0017] S102, based on the abrasion index and uniaxial compressive strength of the surrounding rock to be tested, and the field penetration index and torque penetration index of the TBM, the model is used for prediction processing to generate the excavability index of the surrounding rock to be tested.

[0018] S103, based on the BQ classification method, the surrounding rock to be tested is initially classified and the actual quality index corresponding to the surrounding rock to be tested is generated.

[0019] S104. Based on the TBM classification table for surrounding rock, the excavability index and actual quality indicators of the surrounding rock to be tested are used to determine the TBM grade of the surrounding rock to be tested.

[0020] In S101, the quality indicators of the surrounding rock to be tested and the tunneling data collected by the TBM are obtained; the quality indicators are preprocessed to obtain the abrasion index CAI and uniaxial compressive strength UCS of the surrounding rock to be tested; the tunneling data is preprocessed to obtain the field penetration index and torque penetration index collected by the TBM; among them, the tunneling data includes: the thrust and torque of the TBM single cutter, as well as the penetration and net tunneling speed PR of the TBM.

[0021] In S102, the abrasion index and uniaxial compressive strength of the surrounding rock to be tested, as well as the field penetration index (FPI) and torque penetration index (TPI) of the TBM, are input into the model for prediction processing, and the excavability index of the surrounding rock to be tested is output. Here, the excavability index α ranges from 0 to 1. The better the excavability of the surrounding rock, the closer α is to 1, and vice versa.

[0022] In S103, the surrounding rock to be tested is initially classified based on the BQ classification method to obtain the basic quality index of the rock mass corresponding to the surrounding rock to be tested. Then, the basic quality index of the rock mass corresponding to the surrounding rock to be tested is corrected by comprehensively considering the geological factors of the surrounding rock to generate the actual quality index of the surrounding rock to be tested.

[0023] In S104, the established TBM classification table for surrounding rock is obtained; based on the excavability index and actual quality index of the surrounding rock to be tested, the TBM level of the surrounding rock to be tested is queried from the TBM classification table to determine the TBM level of the surrounding rock to be tested.

[0024] For example: According to the threshold corresponding to Grade I surrounding rock in the surrounding rock TBM classification table; if the excavability index of the surrounding rock to be tested is greater than the first preset threshold and the actual quality index of the surrounding rock to be tested is greater than the second preset threshold, then based on the threshold range in the surrounding rock TBM classification table, the TBM grade corresponding to the surrounding rock to be tested is determined to be Grade I.

[0025] This embodiment uses a model to predict and generate the excavability index of the surrounding rock based on the abrasiveness index and uniaxial compressive strength of the surrounding rock to be tested, as well as the field penetration index and torque penetration index of the TBM. Then, based on the BQ classification method, the actual quality index of the surrounding rock to be tested is combined with the excavability index to determine the TBM index of the surrounding rock. Thus, by comprehensively considering TBM tunneling data, surrounding rock abrasiveness, compressive strength, and geological factors, a TBM surrounding rock classification method based on surrounding rock stability and excavability is finally formed, which improves the accuracy of TBM grade prediction for the surrounding rock to be tested.

[0026] In another preferred embodiment of this example, a TBM classification method for tunnel surrounding rock further includes: for any one of a plurality of first surrounding rock samples: obtaining the abrasion index and uniaxial compressive strength corresponding to the first surrounding rock sample, as well as the quasi-net tunneling speed, field penetration index, and torque penetration index when the TBM collects the first surrounding rock sample; using the abrasion index, the uniaxial compressive strength, the field penetration index, and the torque penetration index together as training samples; obtaining the true value of the tunnelability index corresponding to the first surrounding rock sample based on the ratio of the quasi-net tunneling speed to the reference net tunneling speed; using the true value of the tunnelability index as a label, using a BP neural network to train the model on the training samples, and adjusting the model parameters based on the model training results; and training the model based on the training samples and the true value of the tunnelability index corresponding to each of the plurality of first surrounding rock samples to generate a multivariate regression analysis model.

[0027] Specifically, in the early stage of construction, a large amount of TMB tunneling data and surrounding rock quality indicators are obtained by using TBM to test different first surrounding rock samples, thereby establishing a first surrounding rock sample database. After the neural network is established, the model is trained based on several first surrounding rock samples in the first surrounding rock sample database. When the square error between the actual value of the tunnelability index and the predicted value of the tunnelability index corresponding to the first surrounding rock sample is less than expected, a multiple regression analysis model is obtained.

[0028] Here, the quasi-net tunneling speed PR refers to the ratio (mm / min) of the length of continuous tunneling by the TBM in a complete tunneling process to the tunneling time. Generally, when the quasi-net tunneling speed of the TBM is around 3 mm / min, it is considered to have entered the "cannot tunnel" state because the surrounding rock strength is too high, the cutterhead roller has difficulty cutting into the rock mass, and the cutterhead penetration is also maintained at a very low level.

[0029] For example, the Back Propagation (BP) neural network is a traditional neural network, a multi-layer feedforward neural network trained using an error backpropagation algorithm, consisting of an input layer, hidden layers, and an output layer. The main idea is to continuously adjust the thresholds and weights of each layer in both forward and backward propagation using signals until the error becomes acceptable. The activation function introduces nonlinearity into the neurons, allowing the neural network to approximate any nonlinear function. This BP neural network is set to have 5 layers: an input layer, 3 hidden layers, and an output layer. The input layer is fed with the abrasion index and uniaxial compressive strength of the surrounding rock, as well as the field penetration index and torque penetration index of the TBM. The output layer outputs the predicted value of the excavability index of the surrounding rock. Therefore, the input layer has 4 nodes, the output layer has 1 node, and the number of nodes in the hidden layer is determined through further research. After the neural network is established, it is trained using a large sample database. When the squared error between the actual value and the predicted value of the excavability index is less than expected, a multivariate regression analysis model is obtained.

[0030] This implementation uses a BP neural network to construct a multiple regression analysis model, thereby achieving multiple regression analysis of the excavability index α with CAI, UCS, FPI, and TPI; thus improving the accuracy of the multiple regression analysis model in predicting the excavability index of surrounding rock.

[0031] In another preferred embodiment of this example, a TBM classification method for tunnel surrounding rock further includes: obtaining a plurality of quasi-net tunneling speeds based on the quasi-net tunneling speed corresponding to each of the plurality of first surrounding rock samples; and selecting the maximum quasi-net tunneling speed from the plurality of quasi-net tunneling speeds as a reference net tunneling speed.

[0032] Specifically, during model training, each first surrounding rock sample has a corresponding quasi-net tunneling speed. For any first surrounding rock sample: the ratio of the quasi-net tunneling speed to the reference net tunneling speed is used to obtain the true value of the tunnelability index corresponding to the first surrounding rock sample. Thus, each first surrounding rock sample has a corresponding true value of the tunnelability index. When using any first surrounding rock sample for model training, the true value of the tunnelability index corresponding to that first surrounding rock sample is used as the label, and a backpropagation neural network is used to train the model for that first surrounding rock sample. The model parameters are then adjusted based on the model training results.

[0033] Therefore, by normalizing the clean tunneling speed, the true value of the tunnelability index corresponding to each first surrounding rock sample can be obtained, which is beneficial to model training and improves the accuracy of model training.

[0034] In another preferred embodiment of this invention, a TBM grading method for tunnel surrounding rock further includes: for any one of several second surrounding rock samples: based on the abrasion index and uniaxial compressive strength corresponding to the second surrounding rock sample, and the field penetration index and torque penetration index corresponding to the TBM when collecting the second surrounding rock sample; using a multiple regression analysis model for prediction processing to generate the excavability index corresponding to the second surrounding rock sample; performing preliminary grading of the second surrounding rock sample based on the BQ grading method to generate the actual quality index corresponding to the second surrounding rock sample; and based on the excavability index and actual quality index corresponding to each of the several second surrounding rock samples, performing threshold division of the surrounding rock grade to create a surrounding rock TBM grading table.

[0035] Therefore, it is possible to create a TBM classification table for surrounding rock based on the tunnelability index and actual quality indicators, which is beneficial for determining the TBM grade of the surrounding rock to be tested later.

[0036] In another preferred embodiment of this example, the step of acquiring the field penetration index and torque penetration index of the TBM when collecting data from the surrounding rock to be tested includes: acquiring quasi-tunneling data of the TBM when collecting data from the surrounding rock to be tested; the quasi-tunneling data includes at least: the quasi-thrust and quasi-torque of a single cutter of the TBM, as well as the quasi-penetration and quasi-net tunneling speed of the TBM; determining the field penetration index of the TBM when collecting data from the surrounding rock to be tested based on the quasi-thrust of the single cutter of the TBM and the quasi-penetration of the TBM; and determining the torque penetration index of the TBM when collecting data from the surrounding rock to be tested based on the quasi-torque of the single cutter of the TBM and the quasi-penetration of the TBM.

[0037] For example, FPI reflects the ability of the surrounding rock mass to resist cutter penetration. Excluding the influence of non-geological parameters such as cutterhead diameter, thrust, and cutterhead rotation speed, FPI is determined by the ratio of the quasi-thrust to the quasi-penetration of a single TBM cutter. It has a good correlation with geological parameters and tunneling data. The larger the FPI value, the greater the quasi-thrust required to achieve the same cutting depth, indicating that the rock mass is more difficult to tunnel. TPI is determined by the ratio of the quasi-torque to the quasi-penetration of a single TBM cutter, and TPI is a parameter for measuring rock-breaking efficiency based on measured cutterhead torque. The calculation formulas for FPI and TPI are shown in equation (1) below:

[0038]

[0039]

[0040] Among them, F n P is the quasi-thrust of a single TBM blade (unit: kN), P is the quasi-penetration of the TBM (unit: mm / rev), and T is the quasi-torque of a single TBM blade (unit: kN·m).

[0041] In another preferred embodiment of this example, acquiring the pre-tunneling data of the TBM collecting the surrounding rock to be measured includes: acquiring the pre-tunneling data corresponding to the surrounding rock to be measured collected by the TBM during a complete tunneling process; wherein, the complete tunneling process includes: a start-up phase, an ascending phase, a stabilizing phase, a descending phase, and a shutdown phase; based on the pre-net tunneling speed being zero, removing the pre-tunneling data corresponding to the start-up phase and the pre-tunneling data corresponding to the shutdown phase from the pre-tunneling data corresponding to the complete tunneling process using a binary state judgment function to obtain the remaining pre-tunneling data; and removing the pre-tunneling data of the ascending phase and the pre-tunneling data of the descending phase from the remaining pre-tunneling data using a threshold method. The pre-tunneling data of the section is used to obtain the pre-tunneling data corresponding to the stable tunneling stage; and the pre-tunneling data corresponding to the stable tunneling stage is used as candidate tunneling data when the TBM collects the surrounding rock to be measured; the candidate tunneling data includes at least candidate thrust datasets and candidate torque datasets for a single TBM cutter, as well as candidate penetration datasets and candidate net tunneling speed datasets for the TBM; based on the average value of the candidate thrust datasets, the quasi-thrust of a single TBM cutter is determined; based on the average value of the candidate torque datasets, the quasi-torque of a single TBM cutter is determined; based on the average value of the candidate penetration datasets, the quasi-penetration of the TBM is determined; based on the average value of the candidate net tunneling speed datasets, the quasi-tunneling speed of the TBM is determined.

[0042] Specifically, preprocessing extracts valuable data columns such as pre-tunneling data, time, and station number from daily data files. A single TBM tunneling operation can be divided into four phases: startup, ascent, formal tunneling, descent, and shutdown. The startup phase lasts approximately 100 seconds, and the shutdown phase lasts approximately 200 seconds. The pre-tunneling speed in these two phases is zero, and they can be removed using a binary state discrimination function. The ascent phase lasts approximately 10–30 seconds, and the descent phase lasts approximately 20–100 seconds. Since the ascent and descent phases are short and provide limited information, their data is discarded.

[0043] Ascending Phase: During the contact between the cutterhead and the tunnel face and the rotation of the cutterhead, the TBM begins to break the rock. The cutterhead bears the rock-breaking resistance, and various parameters such as cutterhead torque and cutterhead thrust begin to increase, marking the start of the ascending phase in the tunneling process. Therefore, the initial criterion for the start of the ascending phase can be based on the fact that the cutterhead thrust and cutterhead torque rapidly exceed the thresholds of frictional resistance Ff and idle torque Tf, as shown in the following formula (2):

[0044] T > T f ;

[0045] F > F f Equation (2).

[0046] Descent phase: Based on the characteristics of TBM tunneling, the thrust and torque decrease rapidly during the cessation of tunneling. Considering that the cutterhead still rotates for a certain period of time to clear slag and decelerate, the torque value will not drop to 0 rapidly. During this process, no rock is broken, and the torque is mainly the idle torque Tf of the cutterhead during rotation. Therefore, the judgment of the cessation phase is the same as that of the ascent phase.

[0047] Therefore, by preprocessing the pre-tunneling data corresponding to the surrounding rock to be tested collected during a complete TBM tunneling process, the quasi-tunneling data when the TBM collects the surrounding rock to be tested can be accurately obtained, which is beneficial to the prediction of the excavability index of the surrounding rock to be tested and improves the accuracy of the TBM grade determination of the surrounding rock to be tested.

[0048] In another preferred embodiment of this example, the preliminary classification of the surrounding rock to be tested based on the BQ classification method to generate the actual quality index corresponding to the surrounding rock to be tested includes: obtaining the saturated compressive strength and rock integrity coefficient of the surrounding rock to be tested; determining the basic quality index of the surrounding rock to be tested based on the saturated compressive strength and rock integrity coefficient of the surrounding rock to be tested; obtaining the groundwater influence correction coefficient, the weak structural plane attitude influence correction coefficient, and the initial stress state influence correction coefficient of the surrounding rock to be tested; and correcting the basic quality index of the rock mass based on the groundwater influence correction coefficient, the weak structural plane attitude influence correction coefficient, and the initial stress state influence correction coefficient to obtain the actual quality index corresponding to the surrounding rock to be tested.

[0049] For example, the surrounding rock is first preliminarily classified according to the BQ classification method to obtain the modified [BQ] value. Taking into account the modified [BQ] value of the surrounding rock stability index and the excavability index α, the threshold of the surrounding rock grade is divided, thereby obtaining a surrounding rock classification method suitable for TBM.

[0050] The calculation of the BQ value mainly includes the saturated compressive strength R of the surrounding rock to be tested. C The rock mass integrity coefficient K corresponding to the surrounding rock to be tested V When the surrounding rock of an underground cavern is under high ground stress or contains weak structural surfaces and groundwater that are unfavorable to the stability of the rock mass, the groundwater outflow status, the attitude of the main structural surfaces and the initial ground stress status are considered for correction. The calculation formula is as follows (3):

[0051] BQ = 90 + 3R C +250K V ;

[0052] [BQ]=BQ-100(K1+K2+K3) Formula (3);

[0053] In the formula: BQ is the basic quality index of the surrounding rock mass corresponding to the rock to be tested; [BQ] is the actual quality index of the surrounding rock to be tested; K1 is the groundwater influence correction coefficient; K2 is the main weak structural plane occurrence influence correction coefficient; K3 is the initial stress state influence correction coefficient. K1, K2, and K3 are taken according to the "Engineering Rock Mass Classification Standard" (GB / T 50218—2014).

[0054] Additionally, when R C >90K V At +30, with R C =90K v Substitute +30 into the calculation of the BQ value; when K V >0.04R C When +0.4, with K V =0.04R C Substitute +0.4 into the BQ value to calculate.

[0055] Therefore, based on the BQ classification, the basic quality indicators of the rock mass corresponding to the surrounding rock are modified according to the geological factors of the surrounding rock, so as to accurately obtain the actual quality indicators of the surrounding rock and improve the accuracy of the TBM grade determination of the surrounding rock.

[0056] In a preferred embodiment of this example, obtaining the abrasiveness index and uniaxial compressive strength of the surrounding rock to be tested includes: obtaining the abrasiveness index of the surrounding rock to be tested by performing a Cerchar abrasion test on the surrounding rock to be tested; and obtaining the uniaxial compressive strength of the surrounding rock to be tested by performing a uniaxial compression test on the surrounding rock to be tested.

[0057] For example, a Cerchar abrasion test was performed on the surrounding rock to be tested, as follows:

[0058] First, the surrounding rock to be tested is obtained by coring with a coring machine or by on-site sampling, and then processed into... The test involves two steps: first, selecting a relatively flat surface as the friction surface for the surrounding rock to be tested; second, fixing the surrounding rock in the clamping clamp; and third, gently placing the steel needle on the surrounding rock from the upper slot of the steel needle guide ring, ensuring that the "one" direction of the steel needle is aligned with the direction of movement of the surrounding rock; then, gently placing a fixed load of 70N on the steel needle and controlling the stepper motor to move the steel needle at a uniform speed of 10mm on the surrounding rock within 1 minute. Five measurements (using five steel needles) are then performed on the same surrounding rock.

[0059] Following the experimental procedure recommended by the International Society for Rock Mechanics (ISRM), four photographs were taken of the side of each steel needle, and the diameters d1, d2, d3, and d4 of the abraded surface were recorded as shown in Table 1 below.

[0060] Table 1. Steel Needle Measurement Data Recording Table

[0061]

[0062] The Cerchar abrasion index is calculated based on 10 times the average diameter (mm) of the worn steel needle tip. The Cerchar abrasion index is used to classify the surrounding rock under test. By searching international literature related to Cerchar testing, the following five classification standards were summarized, originating from Cerchar Laboratory, Norwegian University of Science and Technology (NTNU), Colorado School of Mines (CSM), American Society for Testing and Materials (ASTM), and International Society for Rock Mechanics (ISRM). Detailed CAI classification intervals and descriptions are shown in Tables 2 to 6 below:

[0063] Table 2. Cerchar laboratory CAI grading (steel needle hardness 54–56)

[0064] CAI range abrasive description <0.3 Non-abrasive 0.3-0.5 Extremely low abrasiveness 0.5-1.0 Slightly abrasive 1.0-2.0 medium abrasive 2.0-4.0 Highly abrasive 4.0-6.0 Extremely abrasive

[0065] Table 3. Norwegian University of Science and Technology CAI Grading (Steel Needle Hardness 43)

[0066]

[0067] Table 4. Colorado School of Mines (CAI) grading (steel needle hardness 56)

[0068]

[0069] Table 5. American Society for Testing and Materials (ASM) CAI Classification

[0070]

[0071] Table 6. CAI (China Association for Rock Mechanics) classification (steel needle hardness 54–56)

[0072] CAI range abrasive description 0.1～0.4 Extremely low 0.5～0.9 Very low 1.0～1.9 LowLow 2.0～2.9 Medium 3.0～3.9 High 4.0～4.9 Very high ≥5 Extremely high

[0073] Through comparison, this experiment adopted the CAI classification recommended by the International Association for Rock Mechanics; the final abrasiveness classification of the surrounding rock to be tested is shown in Table 7 below:

[0074] Table 7. Abrasiveness Classification of Rocks by CAI Value

[0075]

[0076] like Figure 2 The diagram shown is a schematic representation of the structure of a steel needle after wear in one embodiment of the present invention.

[0077] Figure 2 The direction indicated by the arrow is used to indicate the diameter of the abraded surface of the steel needle.

[0078] In particular, regarding the uniaxial compression test of the surrounding rock to be tested, since the damage to the surrounding rock to be tested can be ignored in the abrasive test, in order to reduce sampling costs and time, for the abrasive and uniaxial compressive strength data of the same set of samples, the abrasive test is performed on the surrounding rock to be tested first, and then the uniaxial compression test is performed to improve efficiency and reduce workload.

[0079] Based on the BQ classification, this invention establishes a new surrounding rock classification method suitable for TBMs, taking the quality of the surrounding rock as the benchmark and comprehensively considering the excavability and stability of the surrounding rock. This method is beneficial for construction schedule planning and TBM equipment selection, especially for the selection of cutterhead blade hardness, rigidity, and material, providing a basis for decision-making to ensure efficient TBM construction and cost control.

[0080] The TBM classification method for tunnel surrounding rock in this embodiment will be described in detail below with reference to specific applications.

[0081] A TBM classification method for tunnel surrounding rock includes at least the following steps:

[0082] S1. For any one of the several first surrounding rock samples: obtain the abrasion index and uniaxial compressive strength corresponding to the first surrounding rock sample, as well as the quasi-net tunneling speed, field penetration index, and torque penetration index when the TBM collects the first surrounding rock sample; use the abrasion index, uniaxial compressive strength, field penetration index, and torque penetration index together as training samples; based on the ratio of the quasi-net tunneling speed to the reference net tunneling speed, obtain the true value of the tunnelability index corresponding to the first surrounding rock sample; using the true value of the tunnelability index as the label, use a BP neural network to train the model on the training samples, and adjust the model parameters based on the model training results. Based on the training samples and the true value of the tunnelability index corresponding to each of the several first surrounding rock samples, perform model training to generate a multiple regression analysis model.

[0083] S2, for any one of the several second surrounding rock samples: based on the abrasion index and uniaxial compressive strength corresponding to the second surrounding rock sample, and the field penetration index and torque penetration index corresponding to the TBM when collecting the second surrounding rock sample; a multivariate regression analysis model is used for prediction processing to generate the excavability index corresponding to the second surrounding rock sample; the second surrounding rock sample is preliminarily classified based on the BQ grading method to generate the actual quality index corresponding to the second surrounding rock sample. Based on the excavability index and actual quality index corresponding to each of the several second surrounding rock samples, a threshold division of the surrounding rock grade is performed, thereby creating a surrounding rock TBM grading table.

[0084] S3, the abrasive index of the surrounding rock to be tested is obtained by conducting a Cerchar abrasion test on the surrounding rock to be tested; the uniaxial compressive strength of the surrounding rock to be tested is obtained by conducting a uniaxial compression test on the surrounding rock to be tested.

[0085] Acquire pre-tunneling data corresponding to the surrounding rock to be tested, collected by the TBM during a complete tunneling process. The complete tunneling process includes: a startup phase, an ascending phase, a stabilizing phase, a descending phase, and a shutdown phase. Based on a pre-selected net tunneling speed of zero, remove the pre-tunneling data corresponding to the startup phase and the shutdown phase from the pre-tunneling data corresponding to the complete tunneling process using a binary state judgment function to obtain the remaining pre-tunneling data. Then, remove the pre-tunneling data corresponding to the ascending phase and the descending phase from the remaining pre-tunneling data using a threshold method to obtain the pre-tunneling data corresponding to the stabilizing phase. Use the pre-tunneling data corresponding to the stabilizing phase as candidate tunneling data when the TBM collects data from the surrounding rock to be tested. The candidate tunneling data corresponding to the stabilizing phase includes at least candidate thrust and torque datasets for a single TBM cutter, as well as candidate penetration and candidate net tunneling speed datasets for the TBM. Based on the average value of the candidate thrust dataset, the quasi-thrust of a single TBM cutter is determined; based on the average value of the candidate torque dataset, the quasi-torque of a single TBM cutter is determined; based on the average value of the candidate penetration dataset, the quasi-penetration of the TBM is determined; based on the average value of the candidate net tunneling speed dataset, the quasi-tunneling speed of the TBM is determined. Based on the quasi-thrust of the single TBM cutter and the quasi-penetration of the TBM, the field penetration index when the TBM collects data from the surrounding rock to be tested is determined; based on the quasi-torque of the single TBM cutter and the quasi-penetration of the TBM, the torque penetration index when the TBM collects data from the surrounding rock to be tested is determined.

[0086] S4. Based on the abrasion index and uniaxial compressive strength of the surrounding rock to be tested, as well as the field penetration index and torque penetration index of the TBM, a multivariate regression analysis model is used for prediction processing to generate the excavability index of the surrounding rock to be tested.

[0087] S5. Based on the BQ grading method, the surrounding rock to be tested is initially graded to generate the actual quality index corresponding to the surrounding rock to be tested.

[0088] S6. Based on the TBM classification table for surrounding rock, and based on the excavability index and the actual quality index of the surrounding rock to be tested, determine the TBM level of the surrounding rock to be tested.

[0089] Based on the grading standard of surrounding rock stability, this invention takes into account the excavation method of TBM and the characteristics of surrounding rock failure. It establishes a surrounding rock grading method suitable for TBM with the excavability of surrounding rock as the grading index. Moreover, the surrounding rock grading parameters of TBM are more comprehensive, providing clearer guidance for construction and facilitating construction schedule planning and TBM equipment selection. In particular, it facilitates the selection of cutterhead blade hardness, rigidity, and material, providing a decision-making basis for ensuring efficient TBM construction and cost control.

[0090] The various embodiments of the present invention are implemented through programmed processing using a device with processor functionality. Therefore, in practical engineering, the technical solutions and functions of the various embodiments of the present invention can be encapsulated into various modules.

[0091] like Figure 3 The diagram shown is a structural schematic of a TBM grading device for tunnel surrounding rock provided in an embodiment of the present invention.

[0092] A TBM grading device for tunnel surrounding rock, the device 300 comprising: an acquisition module 301, used to acquire the abrasion index and uniaxial compressive strength of the surrounding rock to be tested, and the field penetration index and torque penetration index of the surrounding rock when a full-face tunnel boring machine (TBM) collects data from the surrounding rock; a prediction module 302, used to generate a tunnelability index of the surrounding rock to be tested by performing prediction processing using a model based on the abrasion index and uniaxial compressive strength of the surrounding rock to be tested, and the field penetration index and torque penetration index of the TBM; a first generation module 303, used to perform preliminary grading of the surrounding rock to be tested based on the BQ grading method, and generate the actual quality index of the surrounding rock to be tested; and a first determination module 304, used to determine the TBM grade of the surrounding rock to be tested based on the tunnelability index and the actual quality index of the surrounding rock to be tested, according to a surrounding rock TBM grading table.

[0093] In a preferred embodiment, the device further includes: a model training module, configured to: acquire the abrasion index and uniaxial compressive strength corresponding to any one of the plurality of first surrounding rock samples, as well as the quasi-net tunneling speed, field penetration index, and torque penetration index when the TBM collects the first surrounding rock sample; use the abrasion index, the uniaxial compressive strength, the field penetration index, and the torque penetration index together as training samples; obtain the true value of the tunnelability index corresponding to the first surrounding rock sample based on the ratio of the quasi-net tunneling speed to the reference net tunneling speed; use the true value of the tunnelability index as a label, perform model training on the training samples using a BP neural network, and adjust the model parameters based on the model training results; and a second generation module, configured to perform model training based on the training samples and the true value of the tunnelability index corresponding to each of the plurality of first surrounding rock samples, and generate a multivariate regression analysis model.

[0094] In a preferred embodiment, the apparatus further includes: an acquisition module, configured to acquire a plurality of quasi-net tunneling speeds based on the quasi-net tunneling speed corresponding to each of the plurality of first surrounding rock samples; and a second determination module, configured to select the maximum quasi-net tunneling speed from the plurality of quasi-net tunneling speeds as a reference net tunneling speed.

[0095] In a preferred embodiment, the device further includes: a third generation module, used for any one of the plurality of second surrounding rock samples: based on the abrasion index and uniaxial compressive strength corresponding to the second surrounding rock sample, and the field penetration index and torque penetration index corresponding to the TBM when collecting the second surrounding rock sample; performing predictive processing using a multiple regression analysis model to generate the excavability index corresponding to the second surrounding rock sample; performing preliminary classification of the second surrounding rock sample based on the BQ classification method to generate the actual quality index corresponding to the second surrounding rock sample; and a creation module, used for performing threshold division of surrounding rock grades based on the excavability index and actual quality index corresponding to each of the plurality of second surrounding rock samples, thereby creating a surrounding rock TBM classification table.

[0096] In a preferred embodiment, the acquisition module includes: an acquisition unit, used to acquire quasi-tunneling data when the TBM collects the surrounding rock to be tested; the quasi-tunneling data includes at least: the quasi-thrust and quasi-torque of a single TBM cutter, and the quasi-penetration and quasi-net tunneling speed of the TBM; a first determination unit, used to determine the field penetration index when the TBM collects the surrounding rock to be tested based on the quasi-thrust and quasi-penetration of the TBM cutter; and a second determination unit, used to determine the torque penetration index when the TBM collects the surrounding rock to be tested based on the quasi-torque and quasi-penetration of the TBM cutter.

[0097] In a preferred embodiment, the acquisition unit includes: an acquisition subunit, used to acquire pre-tunneling data corresponding to the surrounding rock to be measured collected by the TBM during a complete tunneling process; wherein, the complete tunneling process includes: a start-up phase, an ascending phase, a stabilizing phase, a descending phase, and a shutdown phase; a first removal subunit, used to remove the pre-tunneling data corresponding to the start-up phase and the pre-tunneling data corresponding to the shutdown phase from the pre-tunneling data corresponding to the complete tunneling process based on a binary state judgment function, according to a pre-selected net tunneling speed of zero, to obtain the remaining pre-tunneling data; and a second removal subunit, used to remove the pre-tunneling data of the ascending phase and the descending phase from the remaining pre-tunneling data based on a threshold method. The pre-tunneling data is used to obtain the pre-tunneling data corresponding to the stable tunneling stage; and the pre-tunneling data corresponding to the stable tunneling stage is used as candidate tunneling data when the TBM collects the surrounding rock to be measured; the candidate tunneling data includes at least candidate thrust datasets and candidate torque datasets for a single TBM cutter, as well as candidate penetration datasets and candidate net tunneling speed datasets for the TBM; a sub-unit is determined to determine the quasi-thrust of a single TBM cutter based on the average value of the candidate thrust datasets; the quasi-torque of a single TBM cutter based on the average value of the candidate torque datasets; the quasi-penetration of the TBM based on the average value of the candidate penetration datasets; and the quasi-tunneling speed of the TBM based on the average value of the candidate net tunneling speed datasets.

[0098] In a preferred embodiment, the first generation module includes: a first acquisition unit, used to acquire the saturated compressive strength and rock mass integrity coefficient of the surrounding rock to be tested; a determination unit, used to determine the basic quality indicators of the surrounding rock to be tested based on the saturated compressive strength and rock mass integrity coefficient of the surrounding rock to be tested; a second acquisition unit, used to acquire the groundwater influence correction coefficient, the weak structural plane attitude influence correction coefficient, and the initial stress state influence correction coefficient of the surrounding rock to be tested; and a generation unit, used to correct the basic quality indicators of the rock mass based on the groundwater influence correction coefficient, the weak structural plane attitude influence correction coefficient, and the initial stress state influence correction coefficient to obtain the actual quality indicators of the surrounding rock to be tested.

[0099] In a preferred embodiment, the acquisition module includes: a first acquisition unit, used to acquire the abrasion index of the surrounding rock under test by performing a Cerchar abrasion test on the surrounding rock under test; and a second acquisition unit, used to acquire the uniaxial compressive strength of the surrounding rock under test by performing a uniaxial compression test on the surrounding rock under test.

[0100] The above-described apparatus can execute the TBM grading method for tunnel surrounding rock provided in an embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the TBM grading method for tunnel surrounding rock. Technical details not described in detail in this embodiment can be found in the TBM grading method for tunnel surrounding rock provided in an embodiment of the present invention.

[0101] The present invention also provides an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the TBM grading method for tunnel surrounding rock as described in the present invention.

[0102] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0103] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0104] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the methods according to the following embodiments of this application described in the "Exemplary Methods" section above.

[0105] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0106] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0107] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0108] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0109] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0110] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

[0111] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0112] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0113] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A TBM classification method for tunnel surrounding rock, characterized in that, The method comprises: obtaining an abrasiveness index obtained when a Cerchar abrasion test is performed on a to-be-tested surrounding rock and a uniaxial compressive strength obtained when a uniaxial compression test is performed on the to-be-tested surrounding rock, and a field penetration index and a torque penetration index when a full-face tunnel boring machine (TBM) collects the to-be-tested surrounding rock; based on the abrasiveness index and the uniaxial compressive strength corresponding to the to-be-tested surrounding rock, and the field penetration index and the torque penetration index corresponding to the TBM, performing prediction processing by using a model to generate a drivability index corresponding to the to-be-tested surrounding rock; based on the BQ classification method, preliminarily classifying the to-be-tested surrounding rock to generate an actual quality index corresponding to the to-be-tested surrounding rock; according to a surrounding rock TBM classification table, based on the drivability index corresponding to the to-be-tested surrounding rock and the actual quality index corresponding to the to-be-tested surrounding rock, determining a TBM grade corresponding to the to-be-tested surrounding rock; the model is a multiple regression analysis model, and is obtained by the following method: for any first surrounding rock sample in a plurality of first surrounding rock samples: obtaining an abrasiveness index and a uniaxial compressive strength corresponding to the first surrounding rock sample, and a quasi-net excavation speed, a field penetration index and a torque penetration index when the TBM collects the first surrounding rock sample; the abrasiveness index, the uniaxial compressive strength, the field penetration index and the torque penetration index are collectively used as a training sample; based on the ratio of the quasi-net excavation speed to the reference net excavation speed, the drivability index true value corresponding to the first surrounding rock sample is obtained; taking the drivability index true value as a label, using a back propagation (BP) neural network to perform model training on the training sample, and adjusting model parameters based on the model training result; based on the training sample and the drivability index true value corresponding to each of the plurality of first surrounding rock samples, model training is performed to generate the multiple regression analysis model; the surrounding rock TBM classification table is obtained by the following method: for any second surrounding rock sample in a plurality of second surrounding rock samples: based on the abrasiveness index and the uniaxial compressive strength corresponding to the second surrounding rock sample, and the field penetration index and the torque penetration index corresponding to the TBM when the TBM collects the second surrounding rock sample; using a multiple regression analysis model to perform prediction processing to generate a drivability index corresponding to the second surrounding rock sample; based on the BQ classification method, preliminarily classifying the second surrounding rock sample to generate an actual quality index corresponding to the second surrounding rock sample; based on the drivability index and the actual quality index corresponding to each of the plurality of second surrounding rock samples, threshold division of the surrounding rock grade is performed to create a surrounding rock TBM classification table.

2. The method of claim 1, wherein, Further comprising: based on the quasi-net excavation speed corresponding to each of the plurality of first surrounding rock samples, a plurality of quasi-net excavation speeds are obtained; selecting a maximum quasi-excavation speed from the plurality of quasi-net excavation speeds as a reference net excavation speed.

3. The method of claim 1, wherein, the obtaining of the field penetration index and the torque penetration index when the full-face tunnel boring machine (TBM) collects the to-be-tested surrounding rock comprises: obtain quasi-excavation data of the TBM when collecting the surrounding rock to be measured; the quasi-excavation data at least includes quasi-thrust of a single cutter of the TBM, quasi-torque of the single cutter, quasi-penetration of the TBM and quasi-net excavation speed of the TBM; determine, based on the quasi-thrust of the single cutter of the TBM and the quasi-penetration of the TBM, a field penetration index of the TBM when collecting the surrounding rock to be measured; determine, based on the quasi-torque of the single cutter of the TBM and the quasi-penetration of the TBM, a torque penetration index of the TBM when collecting the surrounding rock to be measured.

4. The method of claim 3, wherein, The obtaining of the quasi-excavation data of the TBM when collecting the surrounding rock to be measured comprises: obtain pre-excavation data of the TBM when collecting the surrounding rock to be measured in a complete excavation process; the complete excavation process includes a starting stage, a rising stage, a stable stage, a falling stage and a shutdown stage; remove, based on a binary state judgment function, pre-excavation data corresponding to the starting stage and the shutdown stage from the pre-excavation data corresponding to the complete excavation process according to a preselected net excavation speed of zero, to obtain remaining pre-excavation data; remove, based on a threshold method, pre-excavation data of the rising stage and the falling stage from the remaining pre-excavation data, to obtain pre-excavation data corresponding to a stable excavation stage; and take the pre-excavation data corresponding to the stable excavation stage as candidate excavation data of the TBM when collecting the surrounding rock to be measured; the candidate excavation data at least includes candidate thrust data set and candidate torque data set of the single cutter of the TBM, and candidate penetration data set and candidate net excavation speed data set of the TBM; determine, based on an average value of the candidate thrust data set, the quasi-thrust of the single cutter of the TBM; determine, based on an average value of the candidate torque data set, the quasi-torque of the single cutter of the TBM; determine, based on an average value of the candidate penetration data set, the quasi-penetration of the TBM; and determine, based on an average value of the candidate net excavation speed data set, the quasi-net excavation speed of the TBM.

5. The method of claim 1, wherein, The preliminary grading of the surrounding rock to be measured based on the BQ grading method to generate the actual quality index corresponding to the surrounding rock to be measured comprises: obtain rock mass saturated compressive strength and rock mass integrity coefficient corresponding to the surrounding rock to be measured; determine rock mass basic quality index corresponding to the surrounding rock to be measured based on the rock mass saturated compressive strength and the rock mass integrity coefficient; obtain groundwater influence correction coefficient, soft and weak structural plane occurrence influence correction coefficient and initial stress state influence correction coefficient corresponding to the surrounding rock to be measured; correct the rock mass basic quality index based on the groundwater influence correction coefficient, the soft and weak structural plane occurrence influence correction coefficient and the initial stress state influence correction coefficient, to obtain the actual quality index corresponding to the surrounding rock to be measured.

6. A TBM grading device for tunnel surrounding rock, characterized by, The device comprises: an obtaining module configured to obtain an abrasion index obtained when a Cerchar abrasion test is performed on a surrounding rock to be measured, uniaxial compressive strength obtained when a uniaxial compression test is performed on the surrounding rock to be measured, field penetration index and torque penetration index of a tunnel boring machine (TBM) when the TBM collects the surrounding rock to be measured; The prediction module is configured to generate the drillability index of the to-be-tested surrounding rock by performing prediction processing on the abrasiveness index and the uniaxial compressive strength of the to-be-tested surrounding rock and the field penetration index and the torque penetration index of the TBM based on a model, the model being a multiple regression analysis model, and the model being obtained by the following method: for any first surrounding rock sample in a plurality of first surrounding rock samples, obtaining the abrasiveness index and the uniaxial compressive strength of the first surrounding rock sample and the quasi-net tunneling speed, the field penetration index and the torque penetration index of the TBM when the first surrounding rock sample is collected; taking the abrasiveness index, the uniaxial compressive strength, the field penetration index and the torque penetration index as training samples; obtaining the real value of the drillability index of the first surrounding rock sample based on the ratio of the quasi-net tunneling speed to the reference net tunneling speed; taking the real value of the drillability index as a label, performing model training on the training samples by using a back propagation (BP) neural network, and adjusting model parameters based on a model training result; performing model training based on the training samples and the real value of the drillability index of each of the first surrounding rock samples in the plurality of first surrounding rock samples, and generating the multiple regression analysis model. The first generation module is configured to preliminarily classify the to-be-tested surrounding rock based on a BQ classification method, and generate an actual quality index of the to-be-tested surrounding rock. The first determination module is configured to determine a TBM grade of the to-be-tested surrounding rock based on the drillability index of the to-be-tested surrounding rock and the actual quality index of the to-be-tested surrounding rock according to a surrounding rock TBM classification table, and the surrounding rock TBM classification table is obtained by the following method: for any second surrounding rock sample in a plurality of second surrounding rock samples, performing preliminary classification on the second surrounding rock sample based on the abrasiveness index and the uniaxial compressive strength of the second surrounding rock sample and the field penetration index and the torque penetration index of the TBM when the second surrounding rock sample is collected; generating a drillability index of the second surrounding rock sample by performing prediction processing on the drillability index and the uniaxial compressive strength of the second surrounding rock sample based on a multiple regression analysis model; generating an actual quality index of the second surrounding rock sample by performing preliminary classification on the second surrounding rock sample based on a BQ classification method; performing threshold division of the surrounding rock grade based on the drillability index and the actual quality index of each of the second surrounding rock samples in the plurality of second surrounding rock samples, thereby creating the surrounding rock TBM classification table.

7. A computer readable medium having a computer program stored thereon, the program being executed by a processor to implement the method of any one of claims 1-5.

Images